Is gemini-3.1-pro-preview-low good at Structured Output?
gemini-3.1-pro-preview-low ranks #9 of 43 for Structured Output — excellent. The top pick for this task is qwen3.7-max-low.
gemini-3.1-pro-preview-low on each Structured Output sub-task
| Missing & Ambiguous Data | 100.0/100 | #7 |
| Transformation | 100.0/100 | #1 |
| Schema Adherence | 100.0/100 | #5 |
| Extraction | 94.3/100 | #11 |
| Noisy Structured Output Test | 93.4/100 | #12 |
Real examples, graded
WinNoisy OCR extraction 100/100
“The model perfectly executed the task. It returned strict, unformatted JSON, accurately extracted the noisy text without fabricating clean values, correctly handled the unreadable field with a null value, and provided a sensible confidence mapping.”
Frequently asked
Is gemini-3.1-pro-preview-low good at Structured Output?
gemini-3.1-pro-preview-low ranks #9 of 43 models we tested for Structured Output, scoring excellent.
What is gemini-3.1-pro-preview-low's strongest Structured Output skill?
Its best sub-task here is Missing & Ambiguous Data.
This page is Spring Prompt, running
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals